AI-native Software Engineer
We are looking for AI-native Engineers who can build applications using AI and full-stack
technologies, leveraging modern tools like Copilots, Agents, and LLMs to deliver production-ready solutions.
You will work in an environment where:
- Code is co-created with AI
- Specs are translated into working systems using AI tools
- Speed, quality, and product thinking matter equally
Responsibilities
- Build and scale AI-native applications from prototype to production
- Translate PRDs into working systems using AI-assisted development
- Design and develop full-stack solutions (frontend, backend, APIs)
- Integrate LLMs, RAG pipelines, and embeddings into real-world use cases
- Leverage AI tools (Copilot, Cursor, Claude) to accelerate development
- Optimize performance, cost, and reliability
Requirements
Programming & Backend
- Python (preferred), Node.js / JavaScript
- Experience building APIs (REST/GraphQL)
Frontend
- React or similar frameworks
- Basic UI/API integration understanding
AI / LLMs
- LLM APIs (OpenAI, Anthropic)
- Prompt engineering basics
- RAG and embeddings exposure
- Interaction with agents & agentic workflow (Nice to have)
Tools
- Copilot, Cursor, Claude
- LangChain, LlamaIndex (Nice to have)
Cloud
- AWS / GCP / Azure basics
- Deployment and debugging awareness
Core Skills
- Product thinking and user-focused development
- AI-assisted development workflow
- Strong full-stack fundamentals
- LLM integration and debugging
- AI workflows and automation understanding
- Performance, cost, and reliability awareness
Experience Bands
1–3 Years
- Use AI tools for development and debugging
- Basic prompt engineering and output evaluation
- Build small AI features and API integrations
3–6 Years
- Build end-to-end features independently
- Work on RAG and AI workflows in production
- Improve system performance and reliability
6–8 Years
- Design AI systems and architectures
- Handle ambiguity and lead technical decisions
- Mentor team and define best practices
Nice to Have
- Experience working with agent-based systems and agentic workflows
- Built copilots, internal tools, or automation-driven applications using AI
- Exposure to fast-paced product or startup environments
- Experience in building benchmarking frameworks for LLMs (A/B testing, offline and end-to-end evaluation) to measure quality, latency, and cost trade-offs
- Understanding of LLM proxy patterns including routing, caching, safety filters, and rate limiting across multiple models/vendors
Qualifications
- B.E / B.Tech / M.Tech / MCA
Location
- Pune, India